The generic pending interrupt mechanism moves interrupts from the interrupt
handler on the original target CPU to the new destination CPU. This is
required for x86 and ia64 due to the way the interrupt delivery and
acknowledge works if the interrupts are not remapped.
However that update can fail for various reasons. Some of them are valid
reasons to discard the pending update, but the case, when the previous move
has not been fully cleaned up is not a legit reason to fail.
Check the return value of irq_do_set_affinity() for -EBUSY, which indicates
a pending cleanup, and rearm the pending move in the irq dexcriptor so it's
tried again when the next interrupt arrives.
Fixes: 996c591227d9 ("x86/irq: Plug vector cleanup race")
Signed-off-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
---
kernel/irq/migration.c | 24 ++++++++++++++++++------
1 file changed, 18 insertions(+), 6 deletions(-)
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -38,17 +38,18 @@ bool irq_fixup_move_pending(struct irq_d
void irq_move_masked_irq(struct irq_data *idata)
{
struct irq_desc *desc = irq_data_to_desc(idata);
- struct irq_chip *chip = desc->irq_data.chip;
+ struct irq_data *data = &desc->irq_data;
+ struct irq_chip *chip = data->chip;
- if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
+ if (likely(!irqd_is_setaffinity_pending(data)))
return;
- irqd_clr_move_pending(&desc->irq_data);
+ irqd_clr_move_pending(data);
/*
* Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
*/
- if (irqd_is_per_cpu(&desc->irq_data)) {
+ if (irqd_is_per_cpu(data)) {
WARN_ON(1);
return;
}
@@ -73,9 +74,20 @@ void irq_move_masked_irq(struct irq_data
* For correct operation this depends on the caller
* masking the irqs.
*/
- if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
- irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
+ if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) {
+ int ret;
+ ret = irq_do_set_affinity(data, desc->pending_mask, false);
+ /*
+ * If the there is a cleanup pending in the underlying
+ * vector management, reschedule the move for the next
+ * interrupt. Leave desc->pending_mask intact.
+ */
+ if (ret == -EBUSY) {
+ irqd_set_move_pending(data);
+ return;
+ }
+ }
cpumask_clear(desc->pending_mask);
}
On Mon, Jun 4, 2018 at 8:33 AM, Thomas Gleixner <[email protected]> wrote:
> The generic pending interrupt mechanism moves interrupts from the interrupt
> handler on the original target CPU to the new destination CPU. This is
> required for x86 and ia64 due to the way the interrupt delivery and
> acknowledge works if the interrupts are not remapped.
>
> However that update can fail for various reasons. Some of them are valid
> reasons to discard the pending update, but the case, when the previous move
> has not been fully cleaned up is not a legit reason to fail.
>
> Check the return value of irq_do_set_affinity() for -EBUSY, which indicates
> a pending cleanup, and rearm the pending move in the irq dexcriptor so it's
> tried again when the next interrupt arrives.
>
> Fixes: 996c591227d9 ("x86/irq: Plug vector cleanup race")
> Signed-off-by: Thomas Gleixner <[email protected]>
> Cc: [email protected]
Tested-by: Song Liu <[email protected]>
> ---
> kernel/irq/migration.c | 24 ++++++++++++++++++------
> 1 file changed, 18 insertions(+), 6 deletions(-)
>
> --- a/kernel/irq/migration.c
> +++ b/kernel/irq/migration.c
> @@ -38,17 +38,18 @@ bool irq_fixup_move_pending(struct irq_d
> void irq_move_masked_irq(struct irq_data *idata)
> {
> struct irq_desc *desc = irq_data_to_desc(idata);
> - struct irq_chip *chip = desc->irq_data.chip;
> + struct irq_data *data = &desc->irq_data;
> + struct irq_chip *chip = data->chip;
>
> - if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
> + if (likely(!irqd_is_setaffinity_pending(data)))
> return;
>
> - irqd_clr_move_pending(&desc->irq_data);
> + irqd_clr_move_pending(data);
>
> /*
> * Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
> */
> - if (irqd_is_per_cpu(&desc->irq_data)) {
> + if (irqd_is_per_cpu(data)) {
> WARN_ON(1);
> return;
> }
> @@ -73,9 +74,20 @@ void irq_move_masked_irq(struct irq_data
> * For correct operation this depends on the caller
> * masking the irqs.
> */
> - if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
> - irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
> + if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) {
> + int ret;
>
> + ret = irq_do_set_affinity(data, desc->pending_mask, false);
> + /*
> + * If the there is a cleanup pending in the underlying
> + * vector management, reschedule the move for the next
> + * interrupt. Leave desc->pending_mask intact.
> + */
> + if (ret == -EBUSY) {
> + irqd_set_move_pending(data);
> + return;
> + }
> + }
> cpumask_clear(desc->pending_mask);
> }
>
>
>
Hi Thomas,
At 06/04/2018 11:33 PM, Thomas Gleixner wrote:
> The generic pending interrupt mechanism moves interrupts from the interrupt
> handler on the original target CPU to the new destination CPU. This is
> required for x86 and ia64 due to the way the interrupt delivery and
> acknowledge works if the interrupts are not remapped.
>
> However that update can fail for various reasons. Some of them are valid
> reasons to discard the pending update, but the case, when the previous move
> has not been fully cleaned up is not a legit reason to fail.
>
> Check the return value of irq_do_set_affinity() for -EBUSY, which indicates
> a pending cleanup, and rearm the pending move in the irq dexcriptor so it's
s/dexcriptor/descriptor
> tried again when the next interrupt arrives.
>
> Fixes: 996c591227d9 ("x86/irq: Plug vector cleanup race")
> Signed-off-by: Thomas Gleixner<[email protected]>
> Cc:[email protected]
> ---
> kernel/irq/migration.c | 24 ++++++++++++++++++------
> 1 file changed, 18 insertions(+), 6 deletions(-)
>
> --- a/kernel/irq/migration.c
> +++ b/kernel/irq/migration.c
> @@ -38,17 +38,18 @@ bool irq_fixup_move_pending(struct irq_d
> void irq_move_masked_irq(struct irq_data *idata)
> {
> struct irq_desc *desc = irq_data_to_desc(idata);
> - struct irq_chip *chip = desc->irq_data.chip;
> + struct irq_data *data = &desc->irq_data;
> + struct irq_chip *chip = data->chip;
>
> - if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
> + if (likely(!irqd_is_setaffinity_pending(data)))
> return;
>
> - irqd_clr_move_pending(&desc->irq_data);
> + irqd_clr_move_pending(data);
>
> /*
> * Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
> */
> - if (irqd_is_per_cpu(&desc->irq_data)) {
> + if (irqd_is_per_cpu(data)) {
> WARN_ON(1);
> return;
> }
> @@ -73,9 +74,20 @@ void irq_move_masked_irq(struct irq_data
> * For correct operation this depends on the caller
> * masking the irqs.
> */
> - if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
> - irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
> + if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) {
> + int ret;
>
> + ret = irq_do_set_affinity(data, desc->pending_mask, false);
> + /*
> + * If the there is a cleanup pending in the underlying
s/If the there is/If there is/
Thanks,
dou
Commit-ID: a33a5d2d16cb84bea8d5f5510f3a41aa48b5c467
Gitweb: https://git.kernel.org/tip/a33a5d2d16cb84bea8d5f5510f3a41aa48b5c467
Author: Thomas Gleixner <[email protected]>
AuthorDate: Mon, 4 Jun 2018 17:33:54 +0200
Committer: Thomas Gleixner <[email protected]>
CommitDate: Wed, 6 Jun 2018 15:18:19 +0200
genirq/generic_pending: Do not lose pending affinity update
The generic pending interrupt mechanism moves interrupts from the interrupt
handler on the original target CPU to the new destination CPU. This is
required for x86 and ia64 due to the way the interrupt delivery and
acknowledge works if the interrupts are not remapped.
However that update can fail for various reasons. Some of them are valid
reasons to discard the pending update, but the case, when the previous move
has not been fully cleaned up is not a legit reason to fail.
Check the return value of irq_do_set_affinity() for -EBUSY, which indicates
a pending cleanup, and rearm the pending move in the irq dexcriptor so it's
tried again when the next interrupt arrives.
Fixes: 996c591227d9 ("x86/irq: Plug vector cleanup race")
Signed-off-by: Thomas Gleixner <[email protected]>
Tested-by: Song Liu <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Song Liu <[email protected]>
Cc: Dmitry Safonov <[email protected]>
Cc: [email protected]
Cc: Mike Travis <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Tariq Toukan <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
---
kernel/irq/migration.c | 26 +++++++++++++++++++-------
1 file changed, 19 insertions(+), 7 deletions(-)
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 86ae0eb80b53..8b8cecd18cce 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -38,17 +38,18 @@ bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear)
void irq_move_masked_irq(struct irq_data *idata)
{
struct irq_desc *desc = irq_data_to_desc(idata);
- struct irq_chip *chip = desc->irq_data.chip;
+ struct irq_data *data = &desc->irq_data;
+ struct irq_chip *chip = data->chip;
- if (likely(!irqd_is_setaffinity_pending(&desc->irq_data)))
+ if (likely(!irqd_is_setaffinity_pending(data)))
return;
- irqd_clr_move_pending(&desc->irq_data);
+ irqd_clr_move_pending(data);
/*
* Paranoia: cpu-local interrupts shouldn't be calling in here anyway.
*/
- if (irqd_is_per_cpu(&desc->irq_data)) {
+ if (irqd_is_per_cpu(data)) {
WARN_ON(1);
return;
}
@@ -73,9 +74,20 @@ void irq_move_masked_irq(struct irq_data *idata)
* For correct operation this depends on the caller
* masking the irqs.
*/
- if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
- irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
-
+ if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) {
+ int ret;
+
+ ret = irq_do_set_affinity(data, desc->pending_mask, false);
+ /*
+ * If the there is a cleanup pending in the underlying
+ * vector management, reschedule the move for the next
+ * interrupt. Leave desc->pending_mask intact.
+ */
+ if (ret == -EBUSY) {
+ irqd_set_move_pending(data);
+ return;
+ }
+ }
cpumask_clear(desc->pending_mask);
}